Pre-recorded Sessions: From 4 December 2020 | Live Sessions: 10 – 13 December 2020
4 – 13 December 2020
Q&A for Computer Vision and Image Processing
-
Ultimate Supporter
-
Ultimate Attendee
Date: Friday, December 11th
Time: 11:00am - 12:00pm
Venue: Zoom Room 7
Note: All live sessions will be screened on Singapore Time/GMT+8. Convert your time zone here.
Q&A for DMCR-GAN: Adversarial Denoising for Monte Carlo Renderings with Residual Attention Networks and Hierarchical Features Modulation of Auxiliary Buffers
Author(s)/Presenter(s):
Abstract:
We propose an adversarial approach for denoising Monte Carlo renderings (DMCR-GAN) with residual attention networks and hierarchical features modulation of auxiliary buffers.
Q&A for Learning Illumination from Diverse Portraits
Author(s)/Presenter(s):
Abstract:
We present a state-of-the-art method to estimate HDR, omnidirectional illumination from a single portrait image, essentially using faces as light probes while resolving the illumination/reflectance ambiguity across diverse skin tones.
Q&A for PoseFromGraph: Compact 3-D Pose Estimation using Graphs
Author(s)/Presenter(s):
Abstract:
PoseFromGraph, a light weight pose estimation framework suitable for AR. Our compact graph representations facilitate efficient and category-agnostic pose estimation with reduction in time & memory footprint by 4x.
